• DocumentCode
    604383
  • Title

    PSO-RBFNN based optimized PNN classifier model

  • Author

    Jin Liu ; Xiao Fu ; Xingbin Yao

  • Author_Institution
    Dept. of Fundamental Courses, Air Force Aviation Univ., Changchun, China
  • fYear
    2012
  • fDate
    29-31 Dec. 2012
  • Firstpage
    456
  • Lastpage
    459
  • Abstract
    In this paper, a self-adaptive method of iris boundary detection is presented and the method can segment the iris area accurately regardless of the shapes of iris boundaries. On the same time, a new feature extraction technique based on combination using special Gabor filters and wavelet maxima components is proposed. Finally, The radial basis function neural network (RBFNN) with a particle swarm optimization (PSO) a novel iris iris recognition technique with intelligent classifier is proposed for high performance iris recognition. this paper combines radial basis function neural network (RBFNN) and particle swarm optimization (PSO) for an optimized PNN classifier model. The experimental results reveal the proposed algorithm provides superior performance in iris recognition.
  • Keywords
    Gabor filters; edge detection; image classification; image segmentation; iris recognition; particle swarm optimisation; radial basis function networks; wavelet transforms; Gabor filters; PNN classifier model; PSO-RBFNN; feature extraction technique; intelligent classifier; iris area segmentation; iris boundary detection; iris recognition technique; particle swarm optimization; probabilistic neural network; radial basis function neural network; self-adaptive method; wavelet maxima components; Particle swarm optimization; Probabilistic neural network; RBF neural networks; iris recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Network Technology (ICCSNT), 2012 2nd International Conference on
  • Conference_Location
    Changchun
  • Print_ISBN
    978-1-4673-2963-7
  • Type

    conf

  • DOI
    10.1109/ICCSNT.2012.6525976
  • Filename
    6525976